Power system risk assessment model construction method and power system risk assessment method

Abstract

The invention relates to a risk assessment model construction method of a power system and a risk assessment method of the power system. The method comprises the following steps: acquiring historical abnormal event data of the power system and network topology information of the power system; the historical abnormal event data comprises abnormal event data corresponding to different abnormal events occurring in a historical period of time of the power system; determining scene element association systems corresponding to different abnormal events according to the historical abnormal event data and the network topology information; the scene element association system is used for describing an association relationship among scene elements, and each scene element comprises an event type, a disaster-pregnant environment, safety protection, a disaster-bearing body, a disaster-inducing factor and an emergency measure; according to the scene element association systems corresponding to different abnormal events, constructing a fault tree network of the power system; and constructing a risk assessment model of the power system according to the fault tree network and the historical abnormal event data. By adopting the method, the risk existing in the power system can be accurately evaluated and early warned.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a risk assessment model construction and a risk assessment method for power systems. Background Technology

[0002] In recent years, unconventional risks such as regional conflicts and terrorist attacks have frequently disrupted power grids. These extreme events often lack sufficient warning signs, exhibit significant complexity, and pose potential secondary and derivative hazards. Although the probability of a large-scale power outage is extremely low, the sheer size and interconnectedness of the power system mean that any major failure will spread rapidly, exerting a wide-ranging and profound impact on society, the economy, and national security.

[0003] Traditional fault tree analysis can identify risk factors, but it struggles to handle dynamic and uncertain evolutionary processes; Bayesian networks can handle probabilistic and uncertain information, but their structure is complex. There is an urgent need for a method that integrates the advantages of both to quantitatively analyze power system load loss scenarios and improve risk analysis and emergency decision-making capabilities under extreme conditions. Summary of the Invention

[0004] Therefore, it is necessary to provide a risk assessment model and a risk assessment method for power systems to address the aforementioned technical issues, which can accurately assess and provide early warnings of the risks existing in power systems.

[0005] Firstly, this application provides a method for constructing a risk assessment model for a power system, including:

[0006] Acquire historical abnormal event data of the power system and network topology information of the power system; wherein, the historical abnormal event data includes abnormal event data corresponding to different abnormal events that occurred in the power system within a historical period;

[0007] Based on the historical abnormal event data and the network topology information, a scenario element association system corresponding to different abnormal events is determined; wherein, the scenario element association system is used to describe the relationship between various scenario elements, and each scenario element includes event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor and emergency measures.

[0008] Based on the association system of scenario elements corresponding to different abnormal events, a fault tree network of the power system is constructed.

[0009] Based on the fault tree network and the historical abnormal event data, a risk assessment model for the power system is constructed.

[0010] In one embodiment, determining the context element association system corresponding to different abnormal events based on the historical abnormal event data and the network topology information includes:

[0011] For any abnormal event, the event type and disaster-prone environment of the abnormal event are determined based on the abnormal event data of the abnormal event.

[0012] Based on the abnormal event data corresponding to the same event type and disaster-prone environment as the abnormal event in other abnormal events, and the network topology information, determine the disaster-bearing body, security protection, disaster-causing factors and emergency measures corresponding to the abnormal event;

[0013] Based on the event type, disaster-prone environment, disaster-bearing body, safety protection, disaster-causing factors, and emergency measures corresponding to the abnormal event, a scenario element association system corresponding to the abnormal event is constructed.

[0014] In one embodiment, the fault tree network includes fault trees for different anomalies and the connections between fault trees for different anomalies.

[0015] The construction of the fault tree network of the power system based on the association system of scenario elements corresponding to different abnormal events includes:

[0016] Based on the contextual element association system corresponding to different abnormal events, determine the logical structure between different abnormal events;

[0017] For any abnormal event, a fault tree is constructed based on the context element association system corresponding to the abnormal event.

[0018] Based on the logical structure between different abnormal events, construct the connection relationship between the fault trees of different abnormal events.

[0019] In one embodiment, the fault tree for any abnormal event includes a root node, intermediate nodes, leaf nodes, and the connection relationships between the nodes.

[0020] The step of constructing a fault tree for the abnormal event based on the context element association system corresponding to the abnormal event includes:

[0021] The nodes corresponding to the event type and the disaster-prone environment in the scenario element association system corresponding to the abnormal event are taken as the root node of the abnormal event;

[0022] The node corresponding to the disaster-bearing body in the scenario element association system corresponding to the abnormal event is used as the intermediate node of the abnormal event.

[0023] The nodes corresponding to safety protection, disaster-causing factors, and emergency measures in the scenario element association system corresponding to the abnormal event are taken as the leaf nodes of the abnormal event;

[0024] Based on the relationships between various scenario elements in the scenario element association system corresponding to the abnormal event, the connection relationships between each node are constructed.

[0025] In one embodiment, constructing a risk assessment model for the power system based on the fault tree network and the historical anomaly event data includes:

[0026] The fault tree network is mapped to the Bayesian network of the power system; wherein the Bayesian network includes network nodes and connection edges between each network node, the network node represents a node in the fault tree network, and the connection edges between network nodes represent the connection relationship between each fault tree in the fault tree network;

[0027] Based on the historical abnormal event data, determine the initial state information and initial conditional probability of each network node in the Bayesian network;

[0028] Based on the initial state information and initial conditional probability of each network node, node information of each network node is generated to obtain the risk assessment model of the power system.

[0029] Secondly, this application provides a risk assessment method for power systems, including:

[0030] Obtain the current operating data of the power system when the target abnormal event occurs in the current time period;

[0031] Based on the current operating data, determine the evolution period of the target abnormal event;

[0032] Based on the evolution period and the current operating data, the target state information and target conditional probability of each network node in the risk assessment model are determined; wherein, the risk assessment model is constructed using the power system risk assessment model construction method described in the first aspect above;

[0033] Based on the target state information and target conditional probability of each network node, the initial state information and initial conditional probability of each network node in the risk assessment model are updated to obtain the updated risk assessment model.

[0034] Run the updated risk assessment model to obtain the risk assessment results for the power system.

[0035] Thirdly, this application also provides a device for constructing a risk assessment model for a power system, comprising:

[0036] The information acquisition module is used to acquire historical abnormal event data of the power system and network topology information of the power system; wherein, the historical abnormal event data includes abnormal event data corresponding to different abnormal events that occurred in the power system within a historical period;

[0037] The system construction module is used to determine the scenario element association system corresponding to different abnormal events based on the historical abnormal event data and the network topology information; wherein, the scenario element association system is used to describe the relationship between various scenario elements, and each scenario element includes event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor and emergency measures.

[0038] The network construction module is used to construct the fault tree network of the power system based on the association system of scenario elements corresponding to different abnormal events;

[0039] The model building module is used to build a risk assessment model for the power system based on the fault tree network and the historical abnormal event data.

[0040] Fourthly, this application also provides a risk assessment device for a power system, comprising:

[0041] The data acquisition module is used to acquire the current operating data of the power system when a target abnormal event occurs in the current time period;

[0042] The time period determination module is used to determine the evolution period of the target abnormal event based on the current running data;

[0043] The parameter determination module is used to determine the target state information and target conditional probability of each network node in the risk assessment model based on the evolution period and the current operating data.

[0044] The model update module is used to update the initial state information and initial conditional probability of each network node in the risk assessment model based on the target state information and target conditional probability of each network node, so as to obtain the updated risk assessment model.

[0045] The risk assessment module is used to run the updated risk assessment model to obtain the risk assessment results of the power system.

[0046] Fifthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps provided in the first or second aspect above.

[0047] Sixthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps provided in the first or second aspect above.

[0048] In a seventh aspect, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps provided in the first or second aspect described above.

[0049] The aforementioned power system risk assessment model and method, through a scenario element association system, can uncover element correlations that are difficult to discover through traditional experience. The fault tree network covers major abnormal events in the power system and associates multiple types of faults through shared events, thereby ensuring the predictive accuracy of the constructed power system risk assessment model. Furthermore, based on the constructed power system risk assessment model, and based on the target state information and target conditional probabilities of each network node in the risk assessment model determined by the evolution period and the current operating data, the initial state information and initial conditional probabilities of each network node in the risk assessment model are updated, ensuring the accuracy of the power system risk assessment results obtained based on the updated risk assessment model. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating a method for constructing a risk assessment model for a power system in one embodiment.

[0052] Figure 2 This is a schematic diagram of the scenario element association system constructed in one embodiment;

[0053] Figure 3 This is a schematic diagram illustrating the process of constructing a fault tree network for a power system in one embodiment;

[0054] Figure 4 This is a flowchart illustrating the process of constructing a fault tree for anomalies in one embodiment;

[0055] Figure 5 This is a flowchart illustrating the process of constructing a risk assessment model for a power system in one embodiment;

[0056] Figure 6 This is a flowchart illustrating a risk assessment method for a power system in one embodiment;

[0057] Figure 7 This is a flowchart illustrating a method for constructing a risk assessment model for a power system in another embodiment.

[0058] Figure 8 This is a structural block diagram of a power system risk assessment model construction device in one embodiment;

[0059] Figure 9 This is a structural block diagram of a risk assessment device for a power system in one embodiment;

[0060] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] The power system risk assessment model construction method provided in this application embodiment can be applied to application environments where power systems assess and issue early warnings of abnormal risks. The power system risk assessment model construction method provided in this application embodiment can be executed by a computer device, which can be a server or a terminal with powerful computing capabilities.

[0063] In one exemplary embodiment, such as Figure 1 As shown, a method for constructing a risk assessment model for a power system is provided. Taking the application of this method to a server as an example, the specific steps include:

[0064] S101, acquire historical abnormal event data and network topology information of the power system.

[0065] Historical anomaly data includes anomaly data corresponding to different anomalies occurring in the power system within historical time periods. The power system's network topology information describes the structural information of all electrical equipment and their connections within the power system. Anomalies are major extreme events caused by human-caused or natural disasters.

[0066] Optionally, historical abnormal event data of the power system can be extracted from data acquisition devices such as digital fault recorders, fault waveform recorders, and intelligent electronic devices. These devices can collect time-domain data of electrical quantities such as voltage and current, as well as event data such as relay action records and protection device action logs. Meanwhile, fault repair reports and accident analysis documents from power companies are also important sources of historical abnormal event data.

[0067] Furthermore, network topology information for power systems can typically be obtained from power system planning and design documents and geographic information systems (GIS), which includes the connection relationships and parameter information of components such as transmission lines, busbars, transformers, and circuit breakers. Specialized network topology analysis software can also be used to process real-time operational data and identify the structural relationships between network nodes and branches.

[0068] S102, Based on historical abnormal event data and network topology information, determine the context element association system corresponding to different abnormal events.

[0069] The scenario element association system describes the relationships between various scenario elements, which include event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor, and emergency measures. The disaster-prone environment refers to the external conditions for the occurrence of the event; safety protection refers to the disaster-resistant reinforcement measures for the disaster-bearing body; the disaster-bearing body is the core object of the power grid directly affected by the disaster-causing factor; the disaster-causing factor is the natural or man-made factor that triggers or aggravates the event; and emergency measures are the handling and rescue actions to deal with the event.

[0070] Optionally, the first step is to extract key elements covering the event itself and the system environment from historical anomaly data and network topology information to avoid missing critical influencing factors. Specifically, collect historical anomaly data containing information such as fault type, fault time, weather conditions, protection device operation records, and power outage range, as well as network topology information such as equipment connection relationships, voltage levels, equipment parameters, and circuit breaker status. Clean the data to remove duplicate, erroneous, or incomplete records. Further, fault types, such as short circuits, overloads, and equipment damage, can be extracted from historical anomaly data as the basic classification of scenario elements. Extract information such as meteorological conditions, geological features, and seasonal periods at the time of the fault from the event data, and obtain environmental information such as the geographical area where the equipment is located from the topology to generate a disaster-prone environment. Organize the types, configurations, and operational effects of protection devices in historical anomaly events, as well as structural information related to protection such as redundant lines and backup power supplies in the topology, to generate safety protection information. Based on the equipment list in the network topology, identify the generators, transformers, busbars, transmission lines, and other equipment affected by the fault as disaster-bearing entities. By combining event data and topology analysis, fault causes can be identified, such as major human-caused accidents or significant climate changes, to determine the causative factors. Information on emergency measures taken after faults in historical events, such as load shifting, switching operations, and resource allocation for emergency repairs, can be extracted as emergency response measures.

[0071] Abnormal events are categorized according to faulty equipment or fault mechanism, such as line faults, transformer faults, and bus faults. For each type of event, the relationships between scenario elements are analyzed. Using event type as the core, an element association matrix or hypernetwork model is constructed to record the relationships and strengths of each element.

[0072] Optionally, a scenario element association system can be constructed using the following methods: For any anomalous event, determine the event type and disaster-prone environment based on the anomalous event data; based on the anomalous event data of other anomalous events with the same event type and disaster-prone environment as the anomalous event, and network topology information, determine the disaster-bearing body, safety protection, disaster-causing factors, and emergency measures corresponding to the anomalous event; and construct a scenario element association system corresponding to the anomalous event based on the event type, disaster-prone environment, disaster-bearing body, safety protection, disaster-causing factors, and emergency measures of the corresponding anomalous event. Specifically, the two most critical types of elements can be extracted from the raw data of the target event without relying on external information, ensuring accurate basic classification. Furthermore, using the determined event type and disaster-prone environment as filtering conditions, similar events are found from the historical database, and network topology information is used to supplement structural information to deduce the remaining elements. Taking the event type of the target event as the core, the six types of elements are organized into a structured system according to causal and impact relationships, clarifying the logical relationships between elements. A new scenario element relationship diagram is established based on the mutual influence of "emergency event type - disaster-prone environment - safety protection - disaster-bearing body - disaster-causing factor - emergency activities". For example, Figure 2 The diagram shown is a schematic diagram of the scenario element association system constructed in the embodiments of this application.

[0073] Taking a country's border power system as an example, the type of emergency is: power system load loss under unconventional extreme risks; the disaster-prone environment is: the border of a certain country; the disaster-bearing bodies are: power generation facilities, high-voltage lines along highways, cross-border substations, and communication towers; the safety protection is: low and high; the emergency activities are: mobile power generation vehicles, emergency repairs, cross-border material transportation, and emergency communication deployment.

[0074] It should be noted that existing scenario elements may change during system evolution; some unknown information will gradually become known or partially known over time, and new scenario elements may also emerge. Therefore, it is necessary to update relevant information in real time based on the dynamic evolution of the system, and to revise and improve the established set of scenario elements. The dynamic function of scenario evolution can be described as: S_t=F{ET_t;DF_t;SF_t;SP_t;EF_t;AF_t}. Due to the relative stability of the types of emergencies and the disaster-prone environment, this function can be simplified to: S_t=F{DF_t;SF_t;SP_t;AF_t}, and a scenario evolution model can be constructed based on this.

[0075] S103. Based on the association system of scenario elements corresponding to different abnormal events, construct a fault tree network for the power system.

[0076] The fault tree network of a power system is a network structure that uses graphical logic (events + logic gates) to systematically connect the causal relationships of various abnormal events (top events) in the power system from their root causes (bottom events) to their final consequences. In the embodiments of this application, the fault tree network includes fault trees for different abnormal events and the connection relationships between the fault trees of different abnormal events; the fault tree of any abnormal event includes a root node, intermediate nodes, leaf nodes, and the connection relationships between the nodes.

[0077] Optionally, it is necessary to first establish the correspondence between scenario elements and fault tree events to ensure that each element can be transformed into a component of the fault tree, avoiding logical gaps. Since scenario elements are diverse and complexly interconnected, directly matching the top event (root node), intermediate events (intermediate nodes), and bottom events (leaf nodes) in the fault tree with scenario elements in a one-to-one correspondence often fails to comprehensively and accurately reflect the system's evolution process. To improve the relevance and feasibility of the analysis, the mapping relationship is optimized in this embodiment: the top event is explicitly associated with the type of emergency event in the scenario elements, used to characterize the core occurrence conditions of the overall risk scenario; intermediate events correspond to the disaster-bearing entities, reflecting the key system nodes and facilities that may be affected or fail under the influence of risk; safety protection and emergency activities are categorized as controllable and manageable underlying factors, playing an intervention and blocking role in the fault tree construction and reasoning process, used to simulate system state changes under different protection and response levels, thereby achieving controllable analysis and deduction of the risk chain.

[0078] In the fault tree construction process, event nodes are connected through relationships such as AND and OR gates. To ensure the accuracy of the deduction, it is necessary to first clarify the logical dependencies and triggering conditions between different events and transform them into corresponding logical structures. Based on the established logical relationships, the analysis can be carried out layer by layer from top to bottom, gradually tracing back to the causative factors at the lowest level, clarifying their specific mechanisms of action and their contribution to the entire failure chain. This progressive logical deduction method can not only pinpoint the root cause of system failure but also provide accurate data support for subsequent risk assessment and optimization of protection strategies.

[0079] S104. Construct a risk assessment model for the power system based on fault tree networks and historical anomaly event data.

[0080] Optionally, a risk assessment model can be constructed based on fault tree networks and historical data. The core of this model is to combine the fault logic (fault tree) with the actual probability of occurrence (historical data) to quantify the "probability of fault occurrence" and the "severity of consequences", and finally output the risk level.

[0081] Optionally, using the logical structure of a fault tree network as a framework, the probability of a base event is calculated using historical data, and then the probability of a top event is derived layer by layer upwards. The core issue is solving the problem of calculating the probability of logic gates. In this embodiment, the ratio between the number of historical abnormal events triggered by the base event and the total number of events within the statistical period can be used as the base event probability. Furthermore, different calculation methods are adopted according to the fault tree logic gate type to ensure that the probability propagation conforms to the logical relationship. Combining the actual impact of historical abnormal events and the operating requirements of the power system, a consequence scoring system is constructed from multiple dimensions to avoid evaluation bias caused by a single dimension. A comprehensive risk value is output through the core logic of probability × consequence, and risk levels are divided according to the actual needs of the power system to clarify the control priority. By combining new historical data and fault tree network adjustments, the model is ensured to fit the actual operating conditions of the power system in the long term, avoiding the problem of one-time modeling for lifelong use.

[0082] The aforementioned method for constructing a risk assessment model for a power system involves acquiring historical abnormal event data and network topology information of the power system. The historical abnormal event data includes data on different abnormal events occurring within a historical timeframe. Based on this data and network topology, a scenario element association system is determined for each abnormal event. This system describes the relationships between various scenario elements, including event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor, and emergency measures. A fault tree network for the power system is constructed based on this association system. Finally, a risk assessment model for the power system is built using the fault tree network and historical abnormal event data. This approach, through the scenario element association system, can uncover element relationships that are difficult to discover through traditional experience. The fault tree network covers major abnormal events in the power system and, by sharing event associations across multiple fault types, ensures the predictive accuracy of the constructed power system risk assessment model.

[0083] In one exemplary embodiment, the fault tree network includes fault trees for different anomalous events and the connections between these fault trees; based on this, such as Figure 3 As shown, a method for constructing a fault tree network for a power system is provided, which specifically includes the following steps:

[0084] S301, Based on the context element association system corresponding to different abnormal events, determine the logical structure between different abnormal events.

[0085] The logical structure between different abnormal events includes the logical dependencies and penalty conditions between them.

[0086] Optionally, for any two anomalous events, the correlation logic between them can be explored from two dimensions: element sharing and impact transmission. Specifically, when the contextual elements of two anomalous events overlap (especially causative factors and disaster-inducing environments), they are judged as parallel correlations, meaning that the same source may trigger multiple events. When the consequence (impact attribute) of one event becomes a causative factor or disaster-inducing environment of another event, it is judged as a chain correlation, meaning that the preceding event triggers the following event. The identified logical relationships are then structured to generate a logical structure between different anomalous events.

[0087] S302, For any abnormal event, construct a fault tree for the abnormal event based on the context element association system corresponding to the abnormal event.

[0088] Optionally, for any abnormal event, events are extracted from scenario elements and logic gates are determined strictly according to the top-intermediate-bottom event hierarchy. Further, a fault tree for the abnormal event is constructed based on the extracted time and logic gates.

[0089] S303, based on the logical structure between different abnormal events, construct the connection relationship between the fault trees of different abnormal events.

[0090] Optionally, shared events or newly added transitional events can be used to chain different fault trees into a network, ensuring that the connection logic is consistent with the relationship identified in the first step. For example, if two fault trees have parallel logic, their common bottom event is used as a shared node, and the top events of both fault trees are connected simultaneously. If two fault trees have cascading logic, the top event of the preceding event is used as a newly added intermediate event in the fault tree of the following event, achieving cascading propagation. The rationality of the connections is checked in conjunction with network topology information, and redundant connections are supplemented.

[0091] In this embodiment, the above scheme can construct a logically rigorous and realistic fault tree network that retains the details of individual fault trees while reflecting the relationships between events.

[0092] Optionally, in one embodiment, the fault tree for any abnormal event includes a root node, intermediate nodes, leaf nodes, and the connections between the nodes; based on this, such as Figure 4 As shown, a method for constructing a fault tree for abnormal events is provided, which specifically includes the following steps:

[0093] S401, the nodes corresponding to the event type and the disaster-prone environment in the context element association system corresponding to the abnormal event are taken as the root node of the abnormal event.

[0094] S402, the node corresponding to the disaster-bearing body in the scenario element association system corresponding to the abnormal event is used as the intermediate node of the abnormal event.

[0095] S403 designates the nodes corresponding to safety protection, disaster-causing factors, and emergency measures in the scenario element association system corresponding to the abnormal event as the leaf nodes of the abnormal event.

[0096] Optionally, it is necessary to strictly adhere to the scenario element association system, mapping the six types of elements to three types of nodes to ensure that each element has a clear node affiliation. Specifically, the scenario elements corresponding to the root node are time type and disaster-prone environment. The scenario elements corresponding to intermediate nodes are the disaster-bearing body, and the scenario elements corresponding to leaf nodes are safety protection, disaster-causing factors, and emergency measures.

[0097] S404, Based on the relationship between the context elements in the context element association system corresponding to the abnormal event, construct the connection relationship between each node.

[0098] Optionally, based on the causal and influence relationships between scenario elements, different types of nodes are connected using logic gates to ensure that the connection logic conforms to the fault mechanism. Specifically, during the fault tree construction process, nodes are connected through relationships such as AND and OR logic gates. To ensure the accuracy of the deduction, the logical dependencies and triggering conditions between different events must first be clarified and transformed into corresponding logical structures. Based on the established logical relationships, the analysis can be carried out layer by layer from top to bottom, gradually tracing back to the most fundamental causal factors, clarifying their specific mechanisms of action and their contribution to the entire fault chain. This progressive logical deduction method can not only pinpoint the root cause of system failure but also provide accurate data support for subsequent risk assessment and protection strategy optimization.

[0099] In this embodiment, the nodes corresponding to the event type and the disaster-prone environment in the scenario element association system corresponding to the abnormal event are taken as the root nodes of the abnormal event. The nodes corresponding to the disaster-bearing body in the scenario element association system corresponding to the abnormal event are taken as the intermediate nodes of the abnormal event. The nodes corresponding to safety protection, disaster-causing factors and emergency measures in the scenario element association system corresponding to the abnormal event are taken as the leaf nodes of the abnormal event. Based on the association relationship between each scenario element in the scenario element association system corresponding to the abnormal event, the connection relationship between each node is constructed to ensure that any abnormal event can quickly transform the scenario element into a fault tree node and establish a logically rigorous connection relationship.

[0100] Optionally, in one embodiment, such as Figure 5 As shown, a method for constructing a risk assessment model for a power system is provided, which specifically includes the following steps:

[0101] S501 maps the fault tree network to a Bayesian network of the power system.

[0102] The Bayesian network consists of network nodes and the edges connecting them. A network node represents a node in a fault tree network, and the edges connecting the network nodes represent the connections between fault trees in the fault tree network.

[0103] Optionally, a clear structural mapping exists between fault trees and Bayesian networks. Specifically, the base events in a fault tree network can be mapped one-to-one with network nodes in a Bayesian network, representing the basic state or primary causes of the power system. Logic gates in a fault tree network are mapped to independent network nodes in a Bayesian network, with the time name of the gate's output used as the node representation, ensuring semantic consistency within the Bayesian network. The connections between fault trees in a fault tree network are transformed into directed edges in a Bayesian network; to maintain the accuracy of causal reasoning, the direction of these edges is opposite to the direction of the connections between fault trees, transforming the causal relationship from lower-level events to higher-level events into a probabilistic relationship where higher-level nodes depend on lower-level nodes.

[0104] It should be noted that when the same underlying event in the fault tree occurs multiple times in different branches, it is uniformly represented as a random network node in the Bayesian network to avoid information redundancy and ensure consistency in probability calculation.

[0105] S502, Based on historical abnormal event data, determine the initial state information and initial conditional probability of each network node in the Bayesian network.

[0106] The initial state information is the definition of the possible states of a network node, and the initial conditional probability is the initial probability of a network node occurring in different states.

[0107] Optionally, prior probabilities and conditional probability tables for each node in a Bayesian network can be learned using historical anomaly event data, providing a quantitative basis for risk inference. When constructing a Bayesian network, it is necessary to clearly define the value category and range of each network node. First, based on the physical meaning and business rules of the events or states represented by the network nodes, determine their node type (e.g., binary discrete, multivariate discrete, or continuous). For discrete nodes, it is necessary to combine historical data, expert experience, and standard specifications to set possible state sets, such as "normal / abnormal," "low / medium / high," etc., ensuring they are mutually exclusive and complete. For example, for power system load loss under unconventional extreme risks, the variable value X=1 indicates a relatively minor load loss of 10%~20%; X=2 indicates a relatively severe load loss of approximately 50%; and X=3 indicates a very severe load loss of 80% or more. For continuous nodes, the value range needs to be determined based on the statistical distribution of monitoring data, which can be characterized by piecewise discretization or probability density functions. Subsequently, the dependencies between states are quantified in the conditional probability table of each network node, thereby ensuring that the Bayesian network has consistency, interpretability, and updability in the reasoning and diagnosis process.

[0108] Given that the analyzed events are unconventional and extreme power safety events, and there is a lack of sufficient historical data and empirical evidence, the expert scoring method was prioritized in the modeling process. This method includes: organizing a group of experts in relevant fields to conduct multiple rounds of independent scoring on the impact relationships between events, summarizing the results, and discussing differences until a unified assessment conclusion is reached; subsequently, by calculating the arithmetic mean of the scores from each expert, an expert evaluation matrix is ​​generated for model analysis. = To investigate the extent to which a particular event affects other events, a cross-influence matrix is ​​calculated using elements from the expert evaluation matrix:

[0109] (1)

[0110] in, For the event Regarding the event Influence coefficient, and events and events The prior probability.

[0111] S503 generates node information for each network node based on its initial state information and initial conditional probability, in order to obtain a risk assessment model for the power system.

[0112] Optionally, the structure and parameters of the Bayesian network can be integrated to form a complete risk assessment model, enabling positive risk prediction and reverse risk diagnosis. It should be noted that the node information for each network node includes, but is not limited to, basic attributes (network node name, variable meaning, and state definition), probability parameters, and associated nodes. Given the root node state, the probability of the top event is calculated to assess the risk level in a specific scenario. If the top event is known, the posterior probability of each bottom event is calculated to pinpoint the most likely cause of the failure. By changing the probability of a certain network node, the change in the probability of the top event is observed to evaluate the effectiveness of prevention and control measures.

[0113] In this embodiment, by converting the fault tree network into a Bayesian network and expressing the association with faults using probabilities, it better fits the actual scenario of multiple factors acting randomly in the power system; thus, the constructed risk prediction model can both predict the probability of risk occurrence and diagnose the root cause of faults, providing two-way support for operation and maintenance decisions.

[0114] In an exemplary embodiment, the risk assessment model constructed based on the power system risk assessment model construction method provided in the above embodiments is as follows: Figure 6 As shown, a risk assessment method for power systems is provided. Taking the application of this method to a server as an example, the specific steps include:

[0115] S601, obtain the current operating data of the power system when a target abnormal event occurs in the current time period.

[0116] The current operational data refers to real-time monitoring data directly related to the target anomaly event, reflecting its dynamic characteristics. In this embodiment, the current operational data includes, but is not limited to, electrical quantity data, equipment status data, environmental data, and topology correlation data.

[0117] Optionally, the current operating data of the power system can be directly collected when the target abnormal event occurs in the current time period.

[0118] S602, Based on the current operating data, determine the evolution period of the target abnormal event.

[0119] It should be noted that, in the embodiments of this application, the evolution period refers to different time periods in the evolution process. The evolution period refers to the time window from the occurrence of the current abnormal event to the stabilization of the risk or the need for intervention measures, and needs to be determined in combination with the event type and historical data.

[0120] S603 determines the target state information and target conditional probability of each network node in the risk assessment model based on the evolution period and current operating data.

[0121] In this embodiment, for extreme power safety event scenarios, two situations—"a single disaster-causing factor acting on a disaster-bearing body of the power system" and "multiple disaster-causing factors coupled acting on a disaster-bearing body of the power system"—are abstracted into simulateable scenario models and embedded into the power grid topology for quantitative analysis. Based on power flow calculation and transient stability analysis, the load loss after a disaster-causing factor impacts a key node of the power grid is calculated, providing data support for risk assessment and emergency decision-making. A single disaster-causing factor scenario is defined as: only one risk source acts on the disaster-bearing body. A multi-disaster-causing factor coupled scenario is defined as: multiple risk sources act on the disaster-bearing body simultaneously or in a time series. These scenarios are mapped to the power grid topology model, ensuring the integrity of node connection relationships, branch parameters, and operational data. AC power flow equations are used to describe the power balance of each node in the power grid. By setting parameter changes caused by disaster-causing factors (such as node offline, impedance changes, and load surges), the power flow equations are resolved to obtain the power flow distribution changes of the affected nodes. By simulating multiple coupled disaster-causing factors in parallel, transient disturbances are introduced to observe the system's stability boundary and fault propagation path.

[0122] In the power flow calculation results, the load reduction in the affected area is statistically analyzed, and the load loss is defined as follows:

[0123] (2)

[0124] in, The total amount of load loss, For the set of affected nodes, For nodes Pre-accident load, For nodes Post-accident load.

[0125] The load loss caused by the impact of disaster-causing factors on critical nodes was obtained in power flow calculation and transient analysis. Then, the target state information and target conditional probability of each network node in the risk assessment model are calculated based on the preset formula.

[0126] S604. Based on the target state information and target conditional probability of each network node, update the initial state information and initial conditional probability of each network node in the risk assessment model to obtain the updated risk assessment model.

[0127] Optionally, the state information and conditional probabilities of each node in the Bayesian network can be dynamically updated for different time periods of the system scenario evolution process to ensure that the model can reflect the latest system operation status and changes in the external environment in real time.

[0128] S605 runs the updated risk assessment model to obtain the risk assessment results for the power system.

[0129] Optionally, the updated network structure can simultaneously perform backward diagnostics (deriving possible causes and their probability distributions from observed results or fault phenomena) and forward inference (predicting possible future events and their probabilities based on known causes or initial states), forming a two-way analysis mechanism. This mechanism can not only quickly locate the root cause after an event occurs, but also predict potential risks in advance during the development of the event, thereby providing more accurate data support for emergency decision-making and resource allocation.

[0130] The aforementioned risk assessment method for power systems involves: acquiring current operational data of the power system when a target anomaly occurs in the current time period; determining the evolution period of the target anomaly based on the current operational data; determining the target state information and target conditional probability of each network node in the risk assessment model based on the evolution period and the current operational data; updating the initial state information and initial conditional probability of each network node in the risk assessment model based on the target state information and target conditional probability of each network node, resulting in an updated risk assessment model; and running the updated risk assessment model to obtain the risk assessment results of the power system. This method achieves dynamic and precise risk assessment by updating the model in real time using current operational data, avoiding the lag of using historical average probabilities to assess real-time risks; focusing on the evolution period of the target anomaly and outputting the key risks within that window, avoiding information overload; and directly linking to the prediction of the effectiveness of emergency measures.

[0131] Figure 7 This is a flowchart illustrating a method for constructing a risk assessment model for a power system in another embodiment. Based on the above embodiments, this embodiment provides an optional example of a method for constructing a risk assessment model for a power system. (Combined with...) Figure 7 The specific implementation process is as follows:

[0132] S701 acquires historical abnormal event data and network topology information of the power system.

[0133] Among them, historical abnormal event data includes abnormal event data corresponding to different abnormal events that occurred in the power system during historical periods.

[0134] S702, based on the abnormal event data of each abnormal event, determine the event type and disaster-prone environment of each abnormal event.

[0135] S703, based on the abnormal event data corresponding to the abnormal event with the same event type and disaster-prone environment as the abnormal event in other abnormal events, as well as network topology information, determine the disaster-bearing body, security protection, disaster-causing factors and emergency measures corresponding to the abnormal event.

[0136] S704. Based on the event type, disaster-prone environment, disaster-bearing body, safety protection, disaster-causing factors, and emergency measures corresponding to each abnormal event, construct a scenario element association system for the abnormal event.

[0137] S705, determine the logical structure between different abnormal events based on the context element association system corresponding to different abnormal events.

[0138] S706: For any abnormal event, construct a fault tree for the abnormal event based on the context element association system corresponding to the abnormal event.

[0139] The fault tree for any abnormal event includes a root node, intermediate nodes, leaf nodes, and the connections between the nodes.

[0140] Optionally, the nodes corresponding to the event type and the disaster-prone environment in the scenario element association system corresponding to the abnormal event are taken as the root nodes of the abnormal event; the nodes corresponding to the disaster-bearing body in the scenario element association system corresponding to the abnormal event are taken as the intermediate nodes of the abnormal event; the nodes corresponding to safety protection, disaster-causing factors and emergency measures in the scenario element association system corresponding to the abnormal event are taken as the leaf nodes of the abnormal event; and the connection relationship between each node is constructed according to the association relationship between each scenario element in the scenario element association system corresponding to the abnormal event.

[0141] S707: Based on the logical structure between different abnormal events, construct the connection relationship between the fault trees of different abnormal events to obtain the fault tree network.

[0142] S708 maps fault tree networks to Bayesian networks of power systems.

[0143] The Bayesian network consists of network nodes and the edges connecting them. A network node represents a node in a fault tree network, and the edges connecting the network nodes represent the connections between fault trees in the fault tree network.

[0144] S709, Based on historical abnormal event data, determine the initial state information and initial conditional probability of each network node in the Bayesian network.

[0145] S710 generates node information for each network node based on the initial state information and initial conditional probability of each network node, in order to obtain a risk assessment model for the power system.

[0146] The specific processes of S701-S710 described above can be found in the description of the above method embodiments. Their implementation principles and technical effects are similar, and will not be repeated here.

[0147] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0148] Based on the same inventive concept, this application also provides a power system risk assessment model construction apparatus for implementing the power system risk assessment model construction method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more power system risk assessment model construction apparatus embodiments provided below can be found in the limitations of the power system risk assessment model construction method described above, and will not be repeated here.

[0149] In one exemplary embodiment, such as Figure 8 As shown, a risk assessment model construction device 800 for a power system is provided, comprising: an information acquisition module 810, a system construction module 820, a network construction module 830, and a model construction module 840, wherein:

[0150] The information acquisition module 810 is used to acquire historical abnormal event data and network topology information of the power system; wherein, the historical abnormal event data includes abnormal event data corresponding to different abnormal events that occurred in the power system during historical periods.

[0151] The system construction module 820 is used to determine the scenario element association system corresponding to different abnormal events based on historical abnormal event data and network topology information. The scenario element association system is used to describe the relationship between various scenario elements, and each scenario element includes event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor and emergency measures.

[0152] Network construction module 830 is used to construct a fault tree network for the power system based on the association system of scenario elements corresponding to different abnormal events.

[0153] Model building module 840 is used to build a risk assessment model for the power system based on fault tree networks and historical anomaly event data.

[0154] In one embodiment, the system construction module 820 is specifically used for:

[0155] For any given anomalous event, the event type and disaster-prone environment of the anomalous event are determined based on the anomalous event data. Based on the anomalous event data of other anomalous events with the same event type and disaster-prone environment as the anomalous event, as well as network topology information, the disaster-bearing entities, security protections, disaster-causing factors, and emergency measures corresponding to the anomalous event are determined. Based on the event type, disaster-prone environment, disaster-bearing entities, security protections, disaster-causing factors, and emergency measures of the anomalous event, a scenario element association system corresponding to the anomalous event is constructed.

[0156] In one embodiment, the fault tree network includes fault trees for different abnormal events and the connections between the fault trees for different abnormal events; the network construction module 830 includes:

[0157] The structure determination unit is used to determine the logical structure between different abnormal events based on the association system of scenario elements corresponding to different abnormal events.

[0158] The fault tree construction unit is used to construct a fault tree for any abnormal event based on the contextual element association system corresponding to the abnormal event.

[0159] The connection building unit is used to construct the connection relationship between the fault trees of different abnormal events based on the logical structure between different abnormal events.

[0160] In one embodiment, the fault tree for any abnormal event includes a root node, intermediate nodes, leaf nodes, and the connections between the nodes; the fault tree construction unit is specifically used for:

[0161] The nodes corresponding to the event type and the disaster-prone environment in the scenario element association system corresponding to the abnormal event are taken as the root nodes of the abnormal event; the nodes corresponding to the disaster-bearing body in the scenario element association system corresponding to the abnormal event are taken as the intermediate nodes of the abnormal event; the nodes corresponding to safety protection, disaster-causing factors and emergency measures in the scenario element association system corresponding to the abnormal event are taken as the leaf nodes of the abnormal event; and the connection relationship between each node is constructed based on the association relationship between each scenario element in the scenario element association system corresponding to the abnormal event.

[0162] In one embodiment, the model building module 840 is specifically used for:

[0163] The fault tree network is mapped to a Bayesian network of the power system. The Bayesian network includes network nodes and connecting edges between them. Network nodes represent nodes in the fault tree network, and connecting edges between them represent the connection relationships between fault trees in the fault tree network. Based on historical abnormal event data, the initial state information and initial conditional probability of each network node in the Bayesian network are determined. Based on the initial state information and initial conditional probability of each network node, node information of each network node is generated to obtain the risk assessment model of the power system.

[0164] Based on the same inventive concept, this application also provides a power system risk assessment device for implementing the power system risk assessment method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more power system risk assessment device embodiments provided below can be found in the limitations of the power system risk assessment method described above, and will not be repeated here.

[0165] In one exemplary embodiment, such as Figure 9 As shown, a risk assessment device 900 for a power system is provided, comprising: a data acquisition module 910, a time period determination module 920, a parameter determination module 930, a model update module 940, and a risk assessment module 950, wherein:

[0166] The data acquisition module 910 is used to acquire the current operating data of the power system when a target abnormal event occurs in the current time period.

[0167] The time period determination module 920 is used to determine the evolution period of the target abnormal event based on the current running data.

[0168] The parameter determination module 930 is used to determine the target state information and target conditional probability of each network node in the risk assessment model based on the evolution period and the current operating data.

[0169] The model update module 940 is used to update the initial state information and initial conditional probability of each network node in the risk assessment model according to the target state information and target conditional probability of each network node, so as to obtain the updated risk assessment model.

[0170] Risk assessment module 950 is used to run the updated risk assessment model to obtain the risk assessment results of the power system.

[0171] Each module in the above-mentioned device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0172] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for constructing a risk assessment model for a power system / or a risk assessment method for a power system.

[0173] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0174] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the power system risk assessment model construction method and / or power system risk assessment method provided in the above embodiments.

[0175] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the power system risk assessment model construction method and / or power system risk assessment method provided in the above embodiments.

[0176] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the power system risk assessment model construction method and / or power system risk assessment method provided in the above embodiments.

[0177] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0178] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0179] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0180] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for constructing a risk assessment model for a power system, characterized in that, The method includes: Acquire historical abnormal event data of the power system and network topology information of the power system; wherein, the historical abnormal event data includes abnormal event data corresponding to different abnormal events that occurred in the power system within a historical period; Based on the historical abnormal event data and the network topology information, a scenario element association system corresponding to different abnormal events is determined; wherein, the scenario element association system is used to describe the relationship between various scenario elements, and each scenario element includes event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor and emergency measures. Based on the association system of scenario elements corresponding to different abnormal events, a fault tree network of the power system is constructed. Based on the fault tree network and the historical abnormal event data, a risk assessment model for the power system is constructed.

2. The method according to claim 1, characterized in that, The step of determining the context element association system corresponding to different abnormal events based on the historical abnormal event data and the network topology information includes: For any abnormal event, the event type and disaster-prone environment of the abnormal event are determined based on the abnormal event data of the abnormal event. Based on the abnormal event data corresponding to the same event type and disaster-prone environment as the abnormal event in other abnormal events, and the network topology information, determine the disaster-bearing body, security protection, disaster-causing factors and emergency measures corresponding to the abnormal event; Based on the event type, disaster-prone environment, disaster-bearing body, safety protection, disaster-causing factors, and emergency measures corresponding to the abnormal event, a scenario element association system corresponding to the abnormal event is constructed.

3. The method according to claim 1, characterized in that, The fault tree network includes fault trees for different abnormal events and the connections between fault trees for different abnormal events. The construction of the fault tree network of the power system based on the association system of scenario elements corresponding to different abnormal events includes: Based on the contextual element association system corresponding to different abnormal events, determine the logical structure between different abnormal events; For any abnormal event, a fault tree is constructed based on the context element association system corresponding to the abnormal event. Based on the logical structure between different abnormal events, construct the connection relationship between the fault trees of different abnormal events.

4. The method according to claim 3, characterized in that, The fault tree for any abnormal event includes the root node, intermediate nodes, leaf nodes, and the connections between the nodes. The step of constructing a fault tree for the abnormal event based on the context element association system corresponding to the abnormal event includes: The nodes corresponding to the event type and the disaster-prone environment in the scenario element association system corresponding to the abnormal event are taken as the root node of the abnormal event; The node corresponding to the disaster-bearing body in the scenario element association system corresponding to the abnormal event is used as the intermediate node of the abnormal event. The nodes corresponding to safety protection, disaster-causing factors, and emergency measures in the scenario element association system corresponding to the abnormal event are taken as the leaf nodes of the abnormal event; Based on the relationships between various scenario elements in the scenario element association system corresponding to the abnormal event, the connection relationships between each node are constructed.

5. The method according to claim 1, characterized in that, The step of constructing a risk assessment model for the power system based on the fault tree network and the historical anomaly event data includes: The fault tree network is mapped to the Bayesian network of the power system; wherein the Bayesian network includes network nodes and connection edges between each network node, the network node represents a node in the fault tree network, and the connection edges between network nodes represent the connection relationship between each fault tree in the fault tree network; Based on the historical abnormal event data, determine the initial state information and initial conditional probability of each network node in the Bayesian network; Based on the initial state information and initial conditional probability of each network node, node information of each network node is generated to obtain the risk assessment model of the power system.

6. A risk assessment method for a power system, characterized in that, The method includes: Obtain the current operating data of the power system when the target abnormal event occurs in the current time period; Based on the current operating data, determine the evolution period of the target abnormal event; Based on the evolution period and the current operating data, the target state information and target conditional probability of each network node in the risk assessment model are determined; wherein, the risk assessment model is constructed using the power system risk assessment model construction method described in any one of claims 1-5. Based on the target state information and target conditional probability of each network node, the initial state information and initial conditional probability of each network node in the risk assessment model are updated to obtain the updated risk assessment model. Run the updated risk assessment model to obtain the risk assessment results for the power system.

7. A device for constructing a risk assessment model for a power system, characterized in that, The device includes: The information acquisition module is used to acquire historical abnormal event data of the power system and network topology information of the power system; wherein, the historical abnormal event data includes abnormal event data corresponding to different abnormal events that occurred in the power system within a historical period; The system construction module is used to determine the scenario element association system corresponding to different abnormal events based on the historical abnormal event data and the network topology information; wherein, the scenario element association system is used to describe the relationship between various scenario elements, and each scenario element includes event type, disaster-prone environment, safety protection, disaster-bearing body, disaster-causing factor and emergency measures. The network construction module is used to construct the fault tree network of the power system based on the association system of scenario elements corresponding to different abnormal events; The model building module is used to build a risk assessment model for the power system based on the fault tree network and the historical abnormal event data.

8. A risk assessment device for a power system, characterized in that, The device includes: The data acquisition module is used to acquire the current operating data of the power system when a target abnormal event occurs in the current time period; The time period determination module is used to determine the evolution period of the target abnormal event based on the current running data; The parameter determination module is used to determine the target state information and target conditional probability of each network node in the risk assessment model based on the evolution period and the current operating data; wherein the risk assessment model is constructed by the power system risk assessment model construction method according to any one of claims 1-5. The model update module is used to update the initial state information and initial conditional probability of each network node in the risk assessment model based on the target state information and target conditional probability of each network node, so as to obtain the updated risk assessment model. The risk assessment module is used to run the updated risk assessment model to obtain the risk assessment results of the power system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images